City-Lifeline-Cockpit/.scratch/cockpit-real-data-wayfinding/verify/artifacts/t67/inspect-code-rule.py

import json, collections, re
p='.scratch/cockpit-real-data-wayfinding/verify/artifacts/t67/geom-none.json'
d=json.load(open(p,encoding='utf-8'))
feats=d['data']['features']
def pref(code):
    m=re.match(r'^([A-Za-z]{2})', str(code or ''))
    return m.group(1) if m else '(none)'
# 前缀 × name 里出现的片区词
tab=collections.defaultdict(collections.Counter)
for ft in feats:
    pr=ft.get('properties') or {}
    name=str(pr.get('name') or '')
    words=tuple(w for w in ['城南','城北','太常'] if w in name)
    tab[pref(pr.get('code'))][words]+=1
for k in sorted(tab): print('prefix', k, dict(tab[k]))
print()
# 非 TC/CN 的样本
for ft in feats:
    pr=ft.get('properties') or {}
    if pref(pr.get('code')) in ('GD','YL'):
        print('ODD', json.dumps({kk:pr.get(kk) for kk in ('source','code','name','industry','typeCode','pointType','remark')}, ensure_ascii=False))
print()
# 第二段：行业字母（第 3-4 位）分布，验证"片区+行业+时间"
ind=collections.Counter()
for ft in feats:
    pr=ft.get('properties') or {}
    code=str(pr.get('code') or '')
    if len(code)>=4: ind[(pref(code), code[2:4])]+=1
print('prefix+biz code:', dict(ind))